假设你有一本这样的字典:

{'a': 1,
 'c': {'a': 2,
       'b': {'x': 5,
             'y' : 10}},
 'd': [1, 2, 3]}

你会如何把它平摊成这样:

{'a': 1,
 'c_a': 2,
 'c_b_x': 5,
 'c_b_y': 10,
 'd': [1, 2, 3]}

当前回答

如果你想要平嵌套的字典,并想要所有唯一的键列表,那么这里是解决方案:

def flat_dict_return_unique_key(data, unique_keys=set()):
    if isinstance(data, dict):
        [unique_keys.add(i) for i in data.keys()]
        for each_v in data.values():
            if isinstance(each_v, dict):
                flat_dict_return_unique_key(each_v, unique_keys)
    return list(set(unique_keys))

其他回答

def flatten(unflattened_dict, separator='_'):
    flattened_dict = {}

    for k, v in unflattened_dict.items():
        if isinstance(v, dict):
            sub_flattened_dict = flatten(v, separator)
            for k2, v2 in sub_flattened_dict.items():
                flattened_dict[k + separator + k2] = v2
        else:
            flattened_dict[k] = v

    return flattened_dict

我尝试了本页上的一些解决方案-虽然不是全部-但我尝试的那些都无法处理dict的嵌套列表。

考虑这样一个词典:

d = {
        'owner': {
            'name': {'first_name': 'Steven', 'last_name': 'Smith'},
            'lottery_nums': [1, 2, 3, 'four', '11', None],
            'address': {},
            'tuple': (1, 2, 'three'),
            'tuple_with_dict': (1, 2, 'three', {'is_valid': False}),
            'set': {1, 2, 3, 4, 'five'},
            'children': [
                {'name': {'first_name': 'Jessica',
                          'last_name': 'Smith', },
                 'children': []
                 },
                {'name': {'first_name': 'George',
                          'last_name': 'Smith'},
                 'children': []
                 }
            ]
        }
    }

以下是我的临时解决方案:

def flatten_dict(input_node: dict, key_: str = '', output_dict: dict = {}):
    if isinstance(input_node, dict):
        for key, val in input_node.items():
            new_key = f"{key_}.{key}" if key_ else f"{key}"
            flatten_dict(val, new_key, output_dict)
    elif isinstance(input_node, list):
        for idx, item in enumerate(input_node):
            flatten_dict(item, f"{key_}.{idx}", output_dict)
    else:
        output_dict[key_] = input_node
    return output_dict

生产:

{
  owner.name.first_name: Steven,
  owner.name.last_name: Smith,
  owner.lottery_nums.0: 1,
  owner.lottery_nums.1: 2,
  owner.lottery_nums.2: 3,
  owner.lottery_nums.3: four,
  owner.lottery_nums.4: 11,
  owner.lottery_nums.5: None,
  owner.tuple: (1, 2, 'three'),
  owner.tuple_with_dict: (1, 2, 'three', {'is_valid': False}),
  owner.set: {1, 2, 3, 4, 'five'},
  owner.children.0.name.first_name: Jessica,
  owner.children.0.name.last_name: Smith,
  owner.children.1.name.first_name: George,
  owner.children.1.name.last_name: Smith,
}

一个临时的解决方案,但并不完美。 注意:

它不保留空字典,例如地址:{}k/v对。 它不会将嵌套元组中的字典平铺——尽管使用python元组类似于列表的事实很容易添加它。

基本上与平铺嵌套列表的方法相同,您只需要做额外的工作,按键/值迭代字典,为新字典创建新键,并在最后一步创建字典。

import collections

def flatten(d, parent_key='', sep='_'):
    items = []
    for k, v in d.items():
        new_key = parent_key + sep + k if parent_key else k
        if isinstance(v, collections.MutableMapping):
            items.extend(flatten(v, new_key, sep=sep).items())
        else:
            items.append((new_key, v))
    return dict(items)

>>> flatten({'a': 1, 'c': {'a': 2, 'b': {'x': 5, 'y' : 10}}, 'd': [1, 2, 3]})
{'a': 1, 'c_a': 2, 'c_b_x': 5, 'd': [1, 2, 3], 'c_b_y': 10}

对于Python >= 3.3,将导入更改为from collections。abc导入MutableMapping以避免弃用警告和更改集合。MutableMapping变成MutableMapping。

def flatten_nested_dict(_dict, _str=''):
    '''
    recursive function to flatten a nested dictionary json
    '''
    ret_dict = {}
    for k, v in _dict.items():
        if isinstance(v, dict):
            ret_dict.update(flatten_nested_dict(v, _str = '_'.join([_str, k]).strip('_')))
        elif isinstance(v, list):
            for index, item in enumerate(v):
                if isinstance(item, dict):
                    ret_dict.update(flatten_nested_dict(item,  _str= '_'.join([_str, k, str(index)]).strip('_')))
                else:
                    ret_dict['_'.join([_str, k, str(index)]).strip('_')] = item
        else:
            ret_dict['_'.join([_str, k]).strip('_')] = v
    return ret_dict

上面的答案真的很管用。我只是想加上我写的unflatten函数:

def unflatten(d):
    ud = {}
    for k, v in d.items():
        context = ud
        for sub_key in k.split('_')[:-1]:
            if sub_key not in context:
                context[sub_key] = {}
            context = context[sub_key]
        context[k.split('_')[-1]] = v
    return ud

注意:这并没有解释键中已经存在的'_',就像扁平化的对应物一样。